CN103631939A - Data processing method and data processing device for search engine - Google Patents
Data processing method and data processing device for search engine Download PDFInfo
- Publication number
- CN103631939A CN103631939A CN201310661382.8A CN201310661382A CN103631939A CN 103631939 A CN103631939 A CN 103631939A CN 201310661382 A CN201310661382 A CN 201310661382A CN 103631939 A CN103631939 A CN 103631939A
- Authority
- CN
- China
- Prior art keywords
- data
- search engine
- keyword
- obtaining
- data processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data processing method and a data processing device for a search engine. The data processing method for the search engine comprises the steps of acquiring historical data of the search engine; acquiring a key word received by the search engine; acquiring an adjusting target; and adjusting the keyword received by the search engine on the basis of the historical data of the search engine and the adjusting target. Through the data processing method and the data processing device, an effect for automatically detecting the concentration level of the user access in the online access can be realized.
Description
Technical field
The present invention relates to internet arena, in particular to a kind of data processing method for search engine and device.
Background technology
Along with the effect of search engine marketing (Search Engine Marketing, be called for short SEM) more and more highlights, advertiser is also increasing to the input of SEM, and keyword is also more and more.Such as some big customers' keyword at least several ten thousand, at most tens0000, hundreds of thousands.It is almost impossible that the keyword of magnanimity like this is wanted to be optimized by artificial mode.The efficient management of throwing in order to realize SEM, in correlation technique, generally adopts the technical scheme of Automatic Optimal.
The technical scheme of the Automatic Optimal of main flow is rule-based optimization in the market, wherein, typical rule-based optimization refers to and utilizes predefined series of rules, and when predefined series of rules meets when pre-conditioned, just carry out predefined operation (as adjusted the position, bid, every conversion cost etc. of keyword).
For example, for certain Internet advertising, when the associative key of this Internet advertising is during in lower position, this keyword can bring certain turn over number, and while rising on the position of this keyword, this keyword can bring more turn over number, wherein, transforms and to comprise registration, order, receive a visitor etc.Like this, for above-mentioned keyword, can judge whether it meets successively following pre-conditioned: whether this keyword is effective; In nearest one month, whether the displaying number of this keyword surpasses 1000; In nearest one month, whether the click volume of this keyword surpasses 100; In nearest one month, whether the turn over number of this keyword surpasses 2; Whether the current location of this keyword is No. 1 position etc., wherein, when above-mentioned keyword meet above-mentioned when pre-conditioned, by the upward price adjustment of this keyword 10%.
Such scheme is when keyword changes, and the preset rules corresponding with this keyword tends to lose efficacy.In addition, due to the data out of true of such scheme dependence, so its forecasting accuracy to target (as upward price adjustment 10%) is lower.
For in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target, effective solution is not yet proposed at present.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of data processing method for search engine and device, to solve in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target.
To achieve these goals, according to an aspect of the present invention, provide a kind of data processing method for search engine.Data processing method for search engine according to the present invention comprises: the historical data of obtaining search engine; Obtain the keyword that search engine receives; Obtain adjustment aim; And the keyword that the historical data based on search engine and adjustment aim receive search engine is adjusted.
Further, obtaining the keyword that search engine receives comprises: obtain a plurality of keywords that search engine receives, after obtaining the keyword that search engine receives, data processing method also comprises: obtain the variance data between a plurality of keywords, the keyword adjustment that the historical data based on search engine and adjustment aim receive search engine comprises: the keyword that the historical data based on search engine, adjustment aim and variance data receive search engine is adjusted.
Further, obtaining adjustment aim comprises: the list of schedules of obtaining user optimization; Obtain the target data arranging for the plan in list; And be adjusted target according to target data.
Further, the list of schedules of obtaining user optimization comprises: obtain and meet APO and optimize the list of schedules requiring; According to target data, being adjusted target comprises: access APO API; By access APO API, obtain the result data from APO, wherein, the analysis result of result data for providing for target data; Based on result data, be adjusted target.
Further, after obtaining the historical data of search engine, data processing method also comprises: obtain a plurality of industry data; Historical data and a plurality of industry data are compared, obtain comparative result, the keyword adjustment that the historical data based on search engine and adjustment aim receive search engine comprises: the predicted data that obtains keyword according to comparative result; Based on predicted data, keyword is adjusted.
Further, obtaining adjustment aim comprises: according to APO optimized algorithm, obtain adjustment aim.
To achieve these goals, according to a further aspect in the invention, provide a kind of data processing equipment for search engine.Data processing equipment for search engine according to the present invention comprises: the first acquiring unit, for obtaining the historical data of search engine; Second acquisition unit, the keyword receiving for obtaining search engine; The 3rd acquiring unit, for obtaining adjustment aim; And adjustment unit, keyword search engine being received for the historical data based on search engine and adjustment aim is adjusted.
Further, a plurality of keywords that the first acquiring unit also receives for obtaining search engine, data processing equipment also comprises: the 4th acquiring unit, for after obtaining the keyword that search engine receives, obtain the variance data between a plurality of keywords, the keyword that adjustment unit also receives search engine for the historical data based on search engine, adjustment aim and variance data is adjusted.
Further, the 3rd acquiring unit comprises: the first acquisition module, for obtaining the list of schedules of user optimization; The second acquisition module, for obtaining the target data for the plan setting of list; And first determination module, for being adjusted target according to target data.
Further, the first acquisition module also meets for obtaining the list of schedules that APO optimizes requirement; The first determination module comprises: access submodule, for accessing APO API; Obtain submodule, for obtaining the result data from APO by access APO API, wherein, the analysis result of result data for providing for target data; Determine submodule, for being adjusted target based on result data.
Further, data processing equipment also comprises: the 5th acquiring unit, for after obtaining the historical data of search engine, obtains a plurality of industry data; Comparing unit, for historical data and a plurality of industry data are compared, obtains comparative result, and adjustment unit comprises: the second determination module, for obtain the predicted data of keyword according to comparative result; Adjusting module, for adjusting keyword based on predicted data.
Further, the 3rd acquiring unit is for obtaining adjustment aim according to APO optimized algorithm.
By the present invention, adopt the historical data of obtaining search engine; Obtain the keyword that search engine receives; Obtain adjustment aim; And the keyword that the historical data based on search engine and adjustment aim receive search engine is adjusted, solved in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target, and then reached the effect of Accurate Prediction target.
Accompanying drawing explanation
The accompanying drawing that forms the application's a part is used to provide a further understanding of the present invention, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is according to the process flow diagram of the data processing method for search engine of first embodiment of the invention;
Fig. 2 is according to the process flow diagram of the data processing method for search engine of second embodiment of the invention;
Fig. 3 is according to the structural representation of the data processing equipment for search engine of first embodiment of the invention; And
Fig. 4 is according to the structural representation of the data processing method for search engine of second embodiment of the invention.
Embodiment
It should be noted that, in the situation that not conflicting, embodiment and the feature in embodiment in the application can combine mutually.Describe below with reference to the accompanying drawings and in conjunction with the embodiments the present invention in detail.
In order to make those skilled in the art better understand the present invention program, below in conjunction with the accompanying drawing in the embodiment of the present invention, to being clearly and completely described in the embodiment of the present invention, obviously, described embodiment is only the embodiment of a part of the present invention, rather than whole embodiment.Embodiment based in the present invention, does not make the every other embodiment obtaining under creative work prerequisite those of ordinary skills, all should belong to protection scope of the present invention.
It should be noted that, the term " first " in instructions of the present invention and claims and above-mentioned accompanying drawing, " second " etc. are for distinguishing similar object, and needn't be for describing specific order or precedence.The data that should be appreciated that such use suitably can exchanged in situation, so as embodiments of the invention described herein can with except diagram here or describe those order enforcement.In addition, term " comprises " and " having " and their any distortion, is intended to be to cover not exclusive comprising.
According to embodiments of the invention, provide a kind of data processing method for search engine, the turn over number that should bring for position, bid and keyword by search engine Accurate Prediction popularization plan keyword for the data processing method of search engine and every conversion cost thereof etc.Should be for the computer-processing equipment that may operate in of data processing method of search engine.
Fig. 1 is according to the process flow diagram of the data processing method for search engine of first embodiment of the invention.
As shown in Figure 1, the method comprises that following step S102 is to step S108:
Step S102, obtains the historical data of search engine.
In embodiments of the present invention, the historical data of obtaining search engine can be to obtain the historical data of one or more search platform, and the historical data of obtaining search engine can comprise the historical data of obtaining advertisement account, advertisement promotion plan, advertising unit and advertisement keyword etc., wherein, historical data comprises that advertisement account, advertisement promotion plan, advertising unit and advertisement keyword etc. represent number, click volume, every conversion cost and turn over number etc. in preset time period.Preset time period can need to preset according to user, and for example, preset time period can be 1 month.
It should be noted that, advertisement account comprises one or more popularization plan, and popularization plan comprises one or more unit, and unit comprises one or more keyword, preferably, the historical data of obtaining search engine can be to obtain the historical data of advertisement promotion plan.Because the historical data of popularization plan can reflect the historical effect of advertisement on the whole, the historical data of therefore obtaining advertisement promotion plan more can advertisement represents number, click volume, every conversion cost and turn over number etc.For example, Internet advertising for beauty treatment, can obtain the historical data of this advertisement promotion calculated " double-edged eyelid " keyword, if and obtain the historical data of " manicure " keyword, can not accurately reflect that this is for conversion situation that in the Internet advertising of beauty treatment, relevant keyword brings in history.
After obtaining the historical data of search engine, can to represent number, click volume and the turn over number etc. of the keyword of advertisement, predict by the historical data of the search engine that obtains, and then can adjust according to predicting the outcome the strategy of advertisement promotion plan, for example, adjust position, bid and every conversion cost etc. of keyword.
Step S104, obtains the keyword that search engine receives.
Obtaining the keyword that search engine receives can be one or more keyword obtaining in default popularization plan.For example, for the Internet advertising of beauty treatment, can obtain " double-edged eyelid " keyword of this Internet advertising and/or " augmentation rhinoplasty " keyword etc.
Preferably, obtaining keyword that search engine receives can comprise and obtain a plurality of keywords that search engine receives, like this, can according to the part of speech of a plurality of keywords, with and historical data about the information of performance, flow and conversion etc., adjust the strategy of advertisement promotion plan.
For example, for the Internet advertising of beauty treatment, obtain part of speech that keyword that search engine receives can comprise a plurality of keywords such as " double-edged eyelid ", " augmentation rhinoplasty ", " manicure " that obtain this Internet advertising, with and historical data about the information of performance, flow and conversion etc., adjust the strategy of advertisement promotion plan.
After obtaining the keyword that search engine receives, this data processing method can also comprise:
Step S105, obtains the variance data between a plurality of keywords.
Obtain variance data between a plurality of keywords and can be obtain a plurality of keywords part of speech, with and historical data about the variance data of the aspects such as performance, flow and conversion.
For example, Internet advertising for beauty treatment, " double-edged eyelid ", " augmentation rhinoplasty ", the part of speech of a plurality of keywords such as " manicures " is different, wherein, " double-edged eyelid ", " augmentation rhinoplasty " is the keyword about beauty treatment, and " manicure " is the keyword lower with the beauty treatment degree of correlation, like this, by search " double-edged eyelid ", keywords such as " augmentation rhinoplasties " can bring the larger number that represents to the Internet advertising of this beauty treatment, click volume and turn over number, and can not bring the larger number that represents to the Internet advertising of this beauty treatment by searched key word " manicure ", click volume and turn over number.
Like this, by the variance data of obtaining between a plurality of keywords, can will be able to bring the larger keyword that represents number, click volume and turn over number to screen to Internet advertising, and the keyword of electing on above-mentioned is carried out to emphasis optimization, wherein, to keyword, optimization comprises and adjusts every conversion cost that position, bid and the keyword of keyword is corresponding etc.
Step S106, obtains adjustment aim.
Obtaining adjustment aim can obtain according to user's demand type, and wherein, user's demand type can comprise to be pursued turn over number type and save the cost type that transforms.Owing to pursuing turn over number type, refer to that user can drop into larger conversion cost in order to chase larger turn over number, saving transforms cost type and refers to that reduction changes into originally under the prerequisite that guarantees that turn over number is constant or increase, and therefore for the demand type of pursuing the user of turn over number type and saving conversion cost type, obtaining adjustment aim can be position, bid and every conversion cost etc. of keyword.
Step S108, the keyword that the historical data based on search engine and adjustment aim receive search engine is adjusted.
The keyword adjustment that historical data based on search engine and adjustment aim receive search engine can be that position, bid and the every conversion cost etc. that representing the keyword that turn over number that number, click volume and keyword produce in history etc. receives search engine in the historical data of search engine are adjusted based on keyword.Wherein, the variation tendency of keyword in the historical data of search engine determines the adjustment degree of position, bid and every conversion cost etc. of keyword.
Preferably, the keyword adjustment that the historical data based on search engine and adjustment aim receive search engine can comprise that the keyword that historical data, adjustment aim and the variance data based on search engine receives search engine adjusts.Like this, can be only to bringing the keyword of larger income to adjust to advertisement, thus can reach the effect that improves optimization efficiency.
For example, for the Internet advertising of beauty treatment, a plurality of keywords such as " double-edged eyelid ", " augmentation rhinoplasty ", " manicure ", because keyword " manicure " is lower with the degree of correlation of beauty treatment, therefore, can only to the degree of correlation with beauty treatment higher " double-edged eyelid ", " augmentation rhinoplasty " keyword, be optimized.Wherein, current position when " double-edged eyelid " and " augmentation rhinoplasty ", bid and its turn over number bringing and every conversion cost are as shown in table 1, after the prediction of the data processing method for search engine by the embodiment of the present invention, the optimum position of " double-edged eyelid " and " augmentation rhinoplasty " of prediction, bid and its turn over number bringing and every conversion cost are as shown in table 2, wherein, the average conversion cost of table 1 is (4.00+2.50)/2=3.25, the average conversion cost of table 2 is (3.33+3.125)/2=3.2275, the average conversion cost that can find out table 1 and table 2 is basic identical, but the turn over number of table 1 is 5+2=7, the turn over number of table 2 is 3+8=11, obviously, in embodiments of the present invention, can be according to the position predicting the outcome to keyword, bid and every conversion cost etc. adjust to obtain larger turn over number.
Table 1
| Keyword | Position | Bid (unit) | Turn over number (inferior) | Every conversion cost (unit/time) |
| Double-edged eyelid | 1 | 20 | 5 | 4.00 |
| Augmentation rhinoplasty | 3 | 5 | 2 | 2.50 |
Table 2
| Keyword | Position | Bid (unit) | Turn over number (inferior) | Every conversion cost (unit/time) |
| Double-edged eyelid | 2 | 10 | 3 | 3.33 |
| Augmentation rhinoplasty | 1 | 25 | 8 | 3.125 |
By the embodiment of the present invention, solved in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target, and then reached the effect of Accurate Prediction target.
Fig. 2 is according to the process flow diagram of the data processing method for search engine of second embodiment of the invention.
As shown in Figure 2, should comprise that following step S202 was to step S212 for the data processing method of search engine, this embodiment can be used as preferred implementation embodiment illustrated in fig. 1.
Step S202 and step S204, with step S102 embodiment illustrated in fig. 1 and step S104, do not repeat them here respectively.
Step S206, obtains the list of schedules of user optimization.
Obtain the list that the list of schedules of user optimization can be optimized the keyword in the popularization plan of Internet advertising for obtaining user, wherein, in this list of schedules, comprise keyword and relevant information thereof in one or more popularization plan of above-mentioned Internet advertising, this keyword relevant information can comprise turn over number that position, bid, the keyword of keyword bring and every conversion cost etc.
Preferably, the list of schedules of obtaining user optimization can comprise obtaining and meets Combinatorial Optimization (Adsage Portfolio Optimier, abbreviation APO) list of schedules requiring, wherein, meeting APO optimize to require to refer to and meets the shown keyword of the historical data of search engine and the overall variation trend in relevant information predetermined time cycle thereof.For example, variation tendency according to keyword A in historical data, if the average daily turn over number that in the list of schedules of the user optimization obtaining, keyword A brings is more than or equal to 200, meets APO optimization and require to refer to that preset time period corresponding to historical data of keyword A is 1 week; If the average daily turn over number that the keyword A in the list of schedules of the user optimization obtaining brings is more than or equal to 100 and be less than 200, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 2 weeks; If the average daily turn over number that the keyword A in the list of schedules of the user optimization obtaining brings is more than or equal to 50 and be less than 100, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 3 weeks; If the average daily turn over number that the keyword in the list of schedules of the user optimization obtaining brings is more than or equal to 30 and be less than 50, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 4 weeks; If the average daily turn over number that certain keyword in the list of schedules of the user optimization obtaining brings is less than 30, does not meet APO and optimize requirement not.
Step S208, obtains the target data arranging for the plan in list.
The target data of obtaining for the plan setting in list can comprise position, bid and the target data such as the turn over number bringing and every conversion cost thereof of obtaining one or more keyword in certain popularization plan in list.
Step S210, is adjusted target according to target data.
The more concentrated position situation that for example, can show in the historical data in preset time period according to the target location of the keyword A in popularization plan and keyword A and bid level with and the historical shift number that brings etc. be adjusted target.
Particularly, can according to target data, be adjusted target in the following manner:
Step S2101, access APO application programming interface (Application Programming Interface is called for short API).
In embodiments of the present invention, access APO API can be access APO client, wherein, when user accesses APO client, this APO client can receive user's target data and the optimization face of the target data that receives by judgement is selected corresponding APO API.For example, when target data optimization aspect is order volume, APO client can be called the APO API that optimizes order; When target data optimization aspect is game registration amount, APO client can be called the APO API that optimizes game registration.
Step S2102, obtains the result data from APO by access APO API.
By access APO API, the historical data in target data and APO can be contrasted, after contrasting with historical data, can obtain the result data from APO, wherein, the analysis result of result data for providing for target data.
Step S2103, is adjusted target based on result data.It should be noted that, after being adjusted target, system can complete the adjustment to target data automatically.For example, system can be adjusted into analysis result by target data automatically.
Step S212, the step S108 with embodiment illustrated in fig. 1, does not repeat them here.
In embodiments of the present invention, after step S202 obtains the historical data of search engine, this data processing method can also comprise:
Step S2021, obtains a plurality of industry data.
A plurality of industry data can comprise the data such as the position, bid, turn over number of keyword in the popularization plan of a plurality of industries, the target data of these data for optimizing.
For example, obtain the data that a plurality of industry data can comprise a plurality of industries such as obtaining advertising sector, financial industry and game industry, after getting the data of a plurality of industries, can optimize the turn over number of above-mentioned a plurality of industries, such as optimizing the order numbers of advertising sector, the registration number of the account number of financial industry, game industry etc.
Step S2022, compares historical data and a plurality of industry data, obtains comparative result.
For example, can by the historical data of financial industry and financial industry the target data of optimization compare to obtain comparative result.
Step S2023, obtains the predicted data of keyword according to comparative result.
For example, table 1 is target data, and table 2 is the comparative result obtaining according to table 1 and historical data thereof, and the data in table 2 can be used as the predicted data of target data in table 1.
Like this, step S212 adjusts keyword based on predicted data.
It should be noted that, in the step shown in the process flow diagram of accompanying drawing, can in the computer system such as one group of computer executable instructions, carry out, and, although there is shown logical order in flow process, but in some cases, can carry out shown or described step with the order being different from herein.
According to embodiments of the invention, provide a kind of data processing equipment for search engine, the turn over number that should bring for position, bid and keyword by search engine Accurate Prediction popularization plan keyword for the data processing equipment of search engine and every conversion cost thereof etc.It should be noted that, the data processing equipment for search engine that the embodiment of the present invention provides can be for carrying out the data processing method for search engine of the embodiment of the present invention, and the data processing method for search engine of the embodiment of the present invention also can be carried out by the data processing equipment for search engine of the embodiment of the present invention.
Fig. 3 is according to the structural representation of the data processing equipment for search engine of first embodiment of the invention.
As shown in Figure 3, this device comprises: the first acquiring unit 10, second acquisition unit 20, the 3rd acquiring unit 30 and adjustment unit 40.
The first acquiring unit 10 is for obtaining the historical data of search engine.
In embodiments of the present invention, the historical data that the first acquiring unit 10 obtains search engine can be to obtain the historical data of one or more search platform, and the historical data that the first acquiring unit 10 obtains search engine can comprise the historical data of obtaining advertisement account, advertisement promotion plan, advertising unit and advertisement keyword etc., wherein, historical data comprises that advertisement account, advertisement promotion plan, advertising unit and advertisement keyword etc. represent number, click volume, every conversion cost and turn over number etc. in preset time period.Preset time period can need to preset according to user, and for example, preset time period can be 1 month.
It should be noted that, advertisement account comprises one or more popularization plan, and popularization plan comprises one or more unit, and unit comprises one or more keyword, preferably, to obtain the historical data of search engine can be to obtain the historical data of advertisement promotion plan to the first acquiring unit 10.Because the historical data of popularization plan can reflect the historical effect of advertisement on the whole, the historical data of therefore obtaining advertisement promotion plan more can advertisement represents number, click volume, every conversion cost and turn over number etc.For example, Internet advertising for beauty treatment, the first acquiring unit 10 can obtain the historical data of this advertisement promotion calculated " double-edged eyelid " keyword, if and obtain the historical data of " manicure " keyword, can not accurately reflect that this is for conversion situation that in the Internet advertising of beauty treatment, relevant keyword brings in history.
After obtaining the historical data of search engine, the first acquiring unit 10 can be predicted represent number, click volume and the turn over number etc. of the keyword of advertisement by the historical data of the search engine that obtains, and then can adjust according to predicting the outcome the strategy of advertisement promotion plan, for example, adjust position, bid and every conversion cost etc. of keyword.
The keyword that second acquisition unit 20 receives for obtaining search engine.
It can be one or more keyword obtaining in default popularization plan that second acquisition unit 20 obtains the keyword that search engine receives.For example, for the Internet advertising of beauty treatment, second acquisition unit 20 can obtain " double-edged eyelid " keyword of this Internet advertising and/or " augmentation rhinoplasty " keyword etc.
Preferably, second acquisition unit 20 obtains keyword that search engine receives and can comprise and obtain a plurality of keywords that search engine receives, like this, can according to the part of speech of a plurality of keywords, with and historical data about the information of performance, flow and conversion etc., adjust the strategy of advertisement promotion plan.
For example, for the Internet advertising of beauty treatment, second acquisition unit 20 obtain part of speech that keyword that search engine receives can comprise a plurality of keywords such as " double-edged eyelid ", " augmentation rhinoplasty ", " manicure " that obtain this Internet advertising, with and historical data about the information of performance, flow and conversion etc., adjust the strategy of advertisement promotion plan.
In embodiments of the present invention, this data processing equipment can also comprise the 4th acquiring unit.The 4th acquiring unit, for after obtaining the keyword that search engine receives, obtains the variance data between a plurality of keywords.
The 4th acquiring unit obtain variance data between a plurality of keywords can be obtain a plurality of keywords part of speech, with and historical data about the variance data of the aspects such as performance, flow and conversion.
For example, Internet advertising for beauty treatment, " double-edged eyelid ", " augmentation rhinoplasty ", the part of speech of a plurality of keywords such as " manicures " is different, wherein, " double-edged eyelid ", " augmentation rhinoplasty " is the keyword about beauty treatment, and " manicure " is the keyword lower with the beauty treatment degree of correlation, like this, by search " double-edged eyelid ", keywords such as " augmentation rhinoplasties " can bring the larger number that represents to the Internet advertising of this beauty treatment, click volume and turn over number, and can not bring the larger number that represents to the Internet advertising of this beauty treatment by searched key word " manicure ", click volume and turn over number.
Like this, by the variance data of obtaining between a plurality of keywords, can will be able to bring the larger keyword that represents number, click volume and turn over number to screen to Internet advertising, and the keyword of electing on above-mentioned is carried out to emphasis optimization, wherein, to keyword, optimization comprises and adjusts every conversion cost that position, bid and the keyword of keyword is corresponding etc.
The 3rd acquiring unit 30 is for obtaining adjustment aim.
The 3rd acquiring unit 30 obtains adjustment aim and can obtain according to user's demand type, and wherein, user's demand type can comprise to be pursued turn over number type and save the cost type that transforms.Owing to pursuing turn over number type, refer to that user can drop into larger conversion cost in order to chase larger turn over number, saving transforms cost type and refers to that reduction changes into originally under the prerequisite that guarantees that turn over number is constant or increase, and therefore for the demand type of pursuing the user of turn over number type and saving conversion cost type, obtaining adjustment aim can be position, bid and every conversion cost etc. of keyword.
The keyword that adjustment unit 40 receives search engine for the historical data based on search engine and adjustment aim is adjusted.
The keyword adjustment that the historical data of adjustment unit 40 based on search engine and adjustment aim receive search engine can be that position, bid and the every conversion cost etc. that representing the keyword that turn over number that number, click volume and keyword produce in history etc. receives search engine in the historical data of search engine are adjusted based on keyword.Wherein, the variation tendency of keyword in the historical data of search engine determines the adjustment degree of position, bid and every conversion cost etc. of keyword.
Preferably, the keyword adjustment that the historical data of adjustment unit 40 based on search engine and adjustment aim receive search engine can comprise that the keyword that historical data, adjustment aim and variance data based on search engine receive search engine adjusts.Like this, can be only to bringing the keyword of larger income to adjust to advertisement, thus can reach the effect that improves optimization efficiency.
For example, for the Internet advertising of beauty treatment, a plurality of keywords such as " double-edged eyelid ", " augmentation rhinoplasty ", " manicure ", because keyword " manicure " is lower with the degree of correlation of beauty treatment, therefore, can only to the degree of correlation with beauty treatment higher " double-edged eyelid ", " augmentation rhinoplasty " keyword, be optimized.Wherein, current position when " double-edged eyelid " and " augmentation rhinoplasty ", bid and its turn over number bringing and every conversion cost are as shown in table 1, after the prediction of the data processing method for search engine by the embodiment of the present invention, the optimum position of " double-edged eyelid " and " augmentation rhinoplasty " of prediction, bid and its turn over number bringing and every conversion cost are as shown in table 2, wherein, the average conversion cost of table 1 is (4.00+2.50)/2=3.25, the average conversion cost of table 2 is (3.33+3.125)/2=3.2275, the average conversion cost that can find out table 1 and table 2 is basic identical, but the turn over number of table 1 is 5+2=7, the turn over number of table 2 is 3+8=11, obviously, in embodiments of the present invention, can be according to the position predicting the outcome to keyword, bid and every conversion cost etc. adjust to obtain larger turn over number.
Table 1
| Keyword | Position | Bid (unit) | Turn over number (inferior) | Every conversion cost (unit/time) |
| Double-edged eyelid | 1 | 20 | 5 | 4.00 |
| Augmentation rhinoplasty | 3 | 5 | 2 | 2.50 |
Table 2
| Keyword | Position | Bid (unit) | Turn over number (inferior) | Every conversion cost (unit/time) |
| Double-edged eyelid | 2 | 10 | 3 | 3.33 |
| Augmentation rhinoplasty | 1 | 25 | 8 | 3.125 |
By the embodiment of the present invention, solved in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target, and then reached the effect of Accurate Prediction target.
Fig. 4 is according to the structural representation of the data processing method for search engine of second embodiment of the invention.
As shown in Figure 4, this embodiment can be used as preferred implementation embodiment illustrated in fig. 3, the data processing equipment for search engine of this embodiment comprises the first acquiring unit 10, second acquisition unit 20, the 3rd acquiring unit 30 and the adjustment unit 40 of the first embodiment, wherein, the 3rd acquiring unit 30 comprises the first acquisition module 301, the second acquisition module 302 and the first determination module 303.
Identical with the first embodiment of the effect of the first acquiring unit 10, second acquisition unit 20 and adjustment unit 40, does not repeat them here.
The first acquisition module 301 is for obtaining the list of schedules of user optimization.
The first acquisition module 301 obtains the list that the list of schedules of user optimization can be optimized the keyword in the popularization plan of Internet advertising for obtaining user, wherein, in this list of schedules, comprise keyword and relevant information thereof in one or more popularization plan of above-mentioned Internet advertising, this keyword relevant information can comprise turn over number that position, bid, the keyword of keyword bring and every conversion cost etc.
Preferably, the list of schedules that the first acquisition module 301 obtains user optimization can comprise obtaining and meets Combinatorial Optimization (Adsage Portfolio Optimier, abbreviation APO) list of schedules requiring, wherein, meeting APO optimize to require to refer to and meets the shown keyword of the historical data of search engine and the overall variation trend in relevant information predetermined time cycle thereof.For example, variation tendency according to keyword A in historical data, if the average daily turn over number that in the list of schedules of the user optimization obtaining, keyword A brings is more than or equal to 200, meets APO optimization and require to refer to that preset time period corresponding to historical data of keyword A is 1 week; If the average daily turn over number that the keyword A in the list of schedules of the user optimization obtaining brings is more than or equal to 100 and be less than 200, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 2 weeks; If the average daily turn over number that the keyword A in the list of schedules of the user optimization obtaining brings is more than or equal to 50 and be less than 100, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 3 weeks; If the average daily turn over number that the keyword in the list of schedules of the user optimization obtaining brings is more than or equal to 30 and be less than 50, meets APO and optimize and require to refer to that preset time period corresponding to historical data of keyword A is 4 weeks; If the average daily turn over number that certain keyword in the list of schedules of the user optimization obtaining brings is less than 30, does not meet APO and optimize requirement not.
The second acquisition module 302 is for obtaining the target data for the plan setting of list.
The target data that the second acquisition module 302 obtains for the plan setting in list can comprise position, bid and the target data such as the turn over number bringing and every conversion cost thereof of obtaining one or more keyword in certain popularization plan in list.
The first determination module 303 is for being adjusted target according to target data.
The more concentrated position situation that for example, can show in the historical data in preset time period according to the target location of the keyword A in popularization plan and keyword A and bid level with and the historical shift number that brings etc. be adjusted target.
Particularly, the first determination module 303 can comprise access submodule, obtain submodule and definite submodule.
Access submodule is used for accessing APO application programming interface (Application Programming Interface is called for short API).
In embodiments of the present invention, access submodule access APO API can be access APO client, wherein, when user accesses APO client, this APO client can receive user's target data and the optimization face of the target data that receives by judgement is selected corresponding APO API.For example, when target data optimization aspect is order volume, APO client can be called the APO API that optimizes order; When target data optimization aspect is game registration amount, APO client can be called the APO API that optimizes game registration.
Obtain submodule for obtaining the result data from APO by access APO API.
Obtain submodule and the historical data in target data and APO can be contrasted by access APO API, after contrasting with historical data, can obtain the result data from APO, wherein, the analysis result of result data for providing for target data.
Determine that submodule is for being adjusted target based on result data.It should be noted that, after being adjusted target, system can complete the adjustment to target data automatically.For example, system can be adjusted into analysis result by target data automatically.
In embodiments of the present invention, this data processing equipment can also comprise: the 5th acquiring unit and comparing unit.
After the 5th acquiring unit obtains the historical data of search engine, obtain a plurality of industry data.
A plurality of industry data can comprise the data such as the position, bid, turn over number of keyword in the popularization plan of a plurality of industries, the target data of these data for optimizing.
For example, obtain the data that a plurality of industry data can comprise a plurality of industries such as obtaining advertising sector, financial industry and game industry, after getting the data of a plurality of industries, can optimize the turn over number of above-mentioned a plurality of industries, such as optimizing the order numbers of advertising sector, the registration number of the account number of financial industry, game industry etc.
Comparing unit, for historical data and a plurality of industry data are compared, obtains comparative result.
For example, can by the historical data of financial industry and financial industry the target data of optimization compare to obtain comparative result.
Like this, in embodiments of the present invention, adjustment unit 40 can comprise the second determination module and adjusting module.
The second determination module is for obtaining the predicted data of keyword according to comparative result.Like this, adjusting module can be based on predicted data, keyword to be adjusted.
For example, table 1 is target data, and table 2 is the comparative result obtaining according to table 1 and historical data thereof, and the data in table 2 can be used as the predicted data of target data in table 1.
As can be seen from the above description, the invention solves in correlation technique for the data processing method of the search engine problem lower to the forecasting accuracy of target, and then reached the effect of Accurate Prediction target.
Obviously, those skilled in the art should be understood that, above-mentioned each module of the present invention or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on the network that a plurality of calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, or they are made into respectively to each integrated circuit modules, or a plurality of modules in them or step are made into single integrated circuit module to be realized.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (12)
1. for a data processing method for search engine, it is characterized in that, comprising:
Obtain the historical data of search engine;
Obtain the keyword that described search engine receives;
Obtain adjustment aim; And
The keyword that historical data based on described search engine and described adjustment aim receive described search engine is adjusted.
2. data processing method according to claim 1, is characterized in that,
Obtaining the keyword that described search engine receives comprises: obtain a plurality of keywords that described search engine receives,
After obtaining the keyword that described search engine receives, described data processing method also comprises: obtain the variance data between described a plurality of keyword,
The keyword adjustment that historical data based on described search engine and described adjustment aim receive described search engine comprises: the keyword that the historical data based on described search engine, described adjustment aim and described variance data receive described search engine is adjusted.
3. data processing method according to claim 1, is characterized in that, obtains described adjustment aim and comprises:
Obtain the list of schedules of user optimization;
Obtain the target data arranging for the plan in described list; And
According to described target data, obtain described adjustment aim.
4. data processing method according to claim 3, is characterized in that,
The list of schedules of obtaining user optimization comprises: obtain and meet the list of schedules that APO optimizes requirement;
According to described target data, obtaining described adjustment aim comprises: access APO API; By accessing described APO API, obtain the result data from described APO, wherein, the analysis result of described result data for providing for described target data; Based on described result data, obtain described adjustment aim.
5. data processing method according to claim 3, is characterized in that,
After obtaining the historical data of described search engine, described data processing method also comprises: obtain a plurality of industry data; Described historical data and described a plurality of industry data are compared, obtain comparative result,
The keyword adjustment that historical data based on described search engine and described adjustment aim receive described search engine comprises: the predicted data that obtains described keyword according to described comparative result; Based on described predicted data, described keyword is adjusted.
6. data processing method according to claim 3, is characterized in that, obtains described adjustment aim and comprises:
According to APO optimized algorithm, obtain described adjustment aim.
7. for a data processing equipment for search engine, it is characterized in that, comprising:
The first acquiring unit, for obtaining the historical data of search engine;
Second acquisition unit, the keyword receiving for obtaining described search engine;
The 3rd acquiring unit, for obtaining adjustment aim; And
Adjustment unit, the keyword described search engine being received for the historical data based on described search engine and described adjustment aim is adjusted.
8. data processing equipment according to claim 7, is characterized in that,
A plurality of keywords that described the first acquiring unit also receives for obtaining described search engine,
Described data processing equipment also comprises: the 4th acquiring unit, for after obtaining the keyword that described search engine receives, obtain the variance data between described a plurality of keyword,
The keyword that described adjustment unit also receives described search engine for the historical data based on described search engine, described adjustment aim and described variance data is adjusted.
9. data processing equipment according to claim 7, is characterized in that, described the 3rd acquiring unit comprises:
The first acquisition module, for obtaining the list of schedules of user optimization;
The second acquisition module, for obtaining the target data for the plan setting of described list; And
The first determination module, for obtaining described adjustment aim according to described target data.
10. data processing equipment according to claim 9, is characterized in that,
Described the first acquisition module also meets for obtaining the list of schedules that APO optimizes requirement;
Described the first determination module comprises: access submodule, for accessing APO API; Obtain submodule, for obtaining the result data from described APO by accessing described APO API, wherein, the analysis result of described result data for providing for described target data; Determine submodule, for obtaining described adjustment aim based on described result data.
11. data processing equipments according to claim 9, is characterized in that,
Described data processing equipment also comprises: the 5th acquiring unit, for after obtaining the historical data of described search engine, obtains a plurality of industry data; Comparing unit, for described historical data and described a plurality of industry data are compared, obtains comparative result,
Described adjustment unit comprises: the second determination module, for obtain the predicted data of described keyword according to described comparative result; Adjusting module, for adjusting described keyword based on described predicted data.
12. data processing equipments according to claim 9, is characterized in that, described the 3rd acquiring unit is for obtaining described adjustment aim according to APO optimized algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310661382.8A CN103631939B (en) | 2013-12-06 | 2013-12-06 | For the data processing method and device of search engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310661382.8A CN103631939B (en) | 2013-12-06 | 2013-12-06 | For the data processing method and device of search engine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103631939A true CN103631939A (en) | 2014-03-12 |
| CN103631939B CN103631939B (en) | 2017-04-05 |
Family
ID=50212980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310661382.8A Active CN103631939B (en) | 2013-12-06 | 2013-12-06 | For the data processing method and device of search engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103631939B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484393A (en) * | 2014-12-12 | 2015-04-01 | 北京国双科技有限公司 | Keyword regulation method and device |
| CN107273508A (en) * | 2017-06-20 | 2017-10-20 | 北京百度网讯科技有限公司 | Information processing method and device based on artificial intelligence |
| CN107436909A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Keyword intelligent optimization method and system |
| CN108230003A (en) * | 2016-12-22 | 2018-06-29 | 北京国双科技有限公司 | The dispensing effect analysis method and device of keyword |
| CN109064221A (en) * | 2018-07-20 | 2018-12-21 | 广州市丰申网络科技有限公司 | AdWords intelligence put-on method and equipment based on big data technology |
| CN109636491A (en) * | 2019-01-25 | 2019-04-16 | 西窗科技(苏州)有限公司 | A kind of optimization method and device that search engine advertisement keyword is launched |
| CN107085573B (en) * | 2016-02-14 | 2020-08-11 | 北京国双科技有限公司 | Hotspot information acquisition method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080046411A1 (en) * | 2004-05-29 | 2008-02-21 | Nhn Corporation | Method and System for Managing the Impressing of the Search Listing Based on Advertisement Group |
| CN101853270A (en) * | 2010-04-29 | 2010-10-06 | 北京艾德思奇科技有限公司 | Method and device for obtaining information position |
| CN102279963A (en) * | 2010-06-11 | 2011-12-14 | 百度在线网络技术（北京）有限公司 | Two-level budget rationality inspection prompting and automatic optimization method, equipment thereof and system thereof |
| CN102567408A (en) * | 2010-12-31 | 2012-07-11 | 阿里巴巴集团控股有限公司 | Method and device for recommending search keyword |
| CN103426097A (en) * | 2012-05-18 | 2013-12-04 | 同程网络科技股份有限公司 | Method suitable for keyword release bid of search engine |
-
2013
- 2013-12-06 CN CN201310661382.8A patent/CN103631939B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080046411A1 (en) * | 2004-05-29 | 2008-02-21 | Nhn Corporation | Method and System for Managing the Impressing of the Search Listing Based on Advertisement Group |
| CN101853270A (en) * | 2010-04-29 | 2010-10-06 | 北京艾德思奇科技有限公司 | Method and device for obtaining information position |
| CN102279963A (en) * | 2010-06-11 | 2011-12-14 | 百度在线网络技术（北京）有限公司 | Two-level budget rationality inspection prompting and automatic optimization method, equipment thereof and system thereof |
| CN102567408A (en) * | 2010-12-31 | 2012-07-11 | 阿里巴巴集团控股有限公司 | Method and device for recommending search keyword |
| CN103426097A (en) * | 2012-05-18 | 2013-12-04 | 同程网络科技股份有限公司 | Method suitable for keyword release bid of search engine |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484393A (en) * | 2014-12-12 | 2015-04-01 | 北京国双科技有限公司 | Keyword regulation method and device |
| CN104484393B (en) * | 2014-12-12 | 2018-11-09 | 北京国双科技有限公司 | Keyword method of adjustment and device |
| CN107085573B (en) * | 2016-02-14 | 2020-08-11 | 北京国双科技有限公司 | Hotspot information acquisition method and device |
| CN107436909A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Keyword intelligent optimization method and system |
| CN108230003A (en) * | 2016-12-22 | 2018-06-29 | 北京国双科技有限公司 | The dispensing effect analysis method and device of keyword |
| CN107273508A (en) * | 2017-06-20 | 2017-10-20 | 北京百度网讯科技有限公司 | Information processing method and device based on artificial intelligence |
| CN107273508B (en) * | 2017-06-20 | 2020-07-10 | 北京百度网讯科技有限公司 | Information processing method and device based on artificial intelligence |
| CN109064221A (en) * | 2018-07-20 | 2018-12-21 | 广州市丰申网络科技有限公司 | AdWords intelligence put-on method and equipment based on big data technology |
| CN109636491A (en) * | 2019-01-25 | 2019-04-16 | 西窗科技(苏州)有限公司 | A kind of optimization method and device that search engine advertisement keyword is launched |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103631939B (en) | 2017-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103631939A (en) | Data processing method and data processing device for search engine | |
| Abedinia et al. | A new feature selection technique for load and price forecast of electrical power systems | |
| Poloczek et al. | Warm starting Bayesian optimization | |
| CN107689008A (en) | A kind of user insures the method and device of behavior prediction | |
| Parmar et al. | A clustering algorithm for supplier base management | |
| Amjady et al. | Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique | |
| CN110119948B (en) | Power consumer credit evaluation method and system based on time-varying weight dynamic combination | |
| Carbonneau et al. | Extensions to the repetitive branch and bound algorithm for globally optimal clusterwise regression | |
| US8255316B2 (en) | Integrated business decision-making system and method | |
| CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
| CN117196787B (en) | Intelligent decision optimization method and system based on artificial intelligence | |
| US11381635B2 (en) | Method of operating a server apparatus for delivering website content, server apparatus and device in communication with server apparatus | |
| CN107688901B (en) | Data adjusting method and device | |
| Morillo Torres et al. | A new model and metaheuristic approach for the energy-based resource-constrained scheduling problem | |
| CN114782201A (en) | Stock recommendation method and device, computer equipment and storage medium | |
| CN117708764A (en) | Intelligent analysis method for student consumption data based on campus card | |
| CN117036001A (en) | Risk identification processing method, device and equipment for transaction service and storage medium | |
| CN116127189A (en) | User operation method, device, equipment and computer storage medium | |
| CN114461630B (en) | Smart attribution analysis method, device, equipment and storage medium | |
| Feng et al. | Dynamic coordination of production planning and sales admission control in the presence of a spot market | |
| Rokicki et al. | Just in time: Controlling temporal performance in crowdsourcing competitions | |
| Liu et al. | Order Allocation for Service Supply Chain Base on the Customer Best Delivery Time Under the Background of Big Data. | |
| CN112818235A (en) | Violation user identification method and device based on associated features and computer equipment | |
| Kanagasabai et al. | Ec2bargainhunter: It's easy to hunt for cost savings on amazon ec2! | |
| Al-Salim et al. | Redesign of production flow lines to postpone product differentiation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170418 Address after: 214000 Wuxi, Jiangsu Province, the New District of the National Software Park Gemini B block, floor 8 Patentee after: Wuxi aide wireless Advertising Co., Ltd. Address before: Wuxi District of Jiangsu city of Wuxi province Zhenze road 214028 No. 18 Wuxi Software Park, Sagittarius B Building Room 501 Patentee before: WUXI ADSAGE SOFTWARE CO., LTD. |
|
| TR01 | Transfer of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Data processing method and device for search engine Effective date of registration: 20201126 Granted publication date: 20170405 Pledgee: Wuxi Branch of Bank of Beijing Co., Ltd Pledgor: Wuxi aide wireless Advertising Co.,Ltd. Registration number: Y2020320010206 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |